Choose Your Plan
Ship more efficient models, reach more users and provide better experiences.
Free
For hobbyists
$0
- Access to ~50 real devices (MacOS, Windows, iOS & Android)
- Support for Core ML, TFLite, ONNX, GGUF and more
- Up to 10 moodel performance benchmarks per day
- Measure inference speed, load time, and peak RAM utilization
- Profile model layer execution across compute units (CPU, GPU, NPU)
Pro
For indie developers and researchers
TBD
We'll get in touch by email as soon as it's ready.
- Access to 100+ real devices
- Priority access to devices
- Higher benchmark limits
Team
For research and engineering teams
Custom
- Additional security for proprietary models and data
- Validate model output correctness across devices
- Evaluate model compression and optimization on performance trade-offs
- Support with model conversion to CoreML, ONNX, etc.
- Weekly calls with founders + direct access on Slack
- Initial free trial
Trusted by
What Our "Team" Customers Say
"RunLocal has reduced the time required for on-device model development from weeks to days, making it possible to assess model quality and performance at scale on different hardware and operating systems. With a high degree of integration with our codebase, a seamless model conversion service and outstanding technical support, RunLocal is a reliable contributor to our model deployment process."
Backed by Investors
(and more)
